Mixture Reduction Algorithms for Uncertain Tracking

Abstract

Bayesian solutions of tracking problems that involve measurement association uncertainty, give rise to Gaussian mixture distributions, which are composed of an ever increasing number of components. To implement such a tracking filter, the growth of components must be controlled by approximating the mixture distribution. A popular and economical scheme is the Probabilistic Data Association Filter (PDAD), which reduces the mixture to a single Gaussian component at each time step. However, this approximation may destroy valuable information, especially if several significant, well spaced components are present. In this report, two new algorithms for reducing Gaussian mixture distributions are presented. These techniques preserve the mean and covariance of the original mixture, and the final approximation is itself a Gaussian mixture. The reduction is achieved by successively merging components or groups of components. The two algorithms have been used to control the growth of components which occurs with the solution to the problem of tracking a single object, in the presence of uniformly distributed false measurements. Simulation results are presented which compare the performance of the resulting tracking filters and the PDAF.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jan 01, 1988
Accession Number
ADA197641

Entities

People

  • D. J. Salmond

Organizations

  • Royal Aircraft Establishment

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Sensors
  • Space
  • Weapons Technologies

DTIC Thesaurus Topics

  • Acceptance Tests
  • Air
  • Algorithms
  • Clustering
  • Computations
  • Covariance
  • Data Association
  • Equations
  • Gaussian Distributions
  • Information Science
  • Kalman Filters
  • Multitarget Tracking
  • Probability
  • Simulations
  • Steady State
  • Surveillance
  • Target Tracking

Readers

  • Applied Combinatorial Optimization and Logic Circuit Design.
  • Statistical inference.
  • Vision Science/Vision Psychology/Cognitive Neuroscience.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - Machine Learning Algorithms
  • Space
  • Space - Space Objects